Semi-supervised learning based named entity recognition for morphologically rich languages

Loading...
Thumbnail Image

Date

2014.

Journal Title

Journal ISSN

Volume Title

Publisher

Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2014.

Abstract

In this study, we addressed the Named Entity Recognition (NER) problem for morphologically rich languages by employing a semi-supervised learning approach based on neural networks. We adopted a fast unsupervised method for learning continuous vector representations of words, and used these representations along with language independent features to develop a NER system. We evaluated our system for the highly in ectional Turkish and Czech languages and obtained better F-score performances than the previously published results for these languages. We improved the state-of-the-art F-score by 2.26% for Turkish and 1.53% for Czech. Unlike the previous state-of-the-art systems developed for these languages, our system does not make use of any language dependent features. Therefore, we believe it can easily be applied to other morphologically rich languages.

Description

Keywords

Citation

Collections